Methods › General › Activation Functions › Squared ReLU

Squared ReLU

15 papers tagged archive 2025-07-28

Introduced by David R. So et al. in Primer: Searching for Efficient Transformers for Language Modeling

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Squared ReLU is an activation function used in the Primer architecture in the feedforward block of the Transformer layer. It is simply squared ReLU activations.

The effectiveness of higher order polynomials can also be observed in other effective Transformer nonlinearities, such as GLU variants like ReGLU and point-wise activations like approximate GELU. However, squared ReLU has drastically different asymptotics as x →inf compared to the most commonly used activation functions: ReLU, GELU and Swish. Squared ReLU does have significant overlap with ReGLU and in fact is equivalent when ReGLU’s U and V weight matrices are the same and squared ReLU is immediately preceded by a linear transformation with weight matrix U. This leads the authors to believe that squared ReLUs capture the benefits of these GLU variants, while being simpler, without additional parameters, and delivering better quality.

PaperSource

Papers archive 2025-07-28

15 shown of 15, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

18 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Language Modeling4
Language Modelling4
CPU1
Common Sense Reasoning1
Coreference Resolution1
Deep Learning1
Diversity1
Epidemiology1
GPU1
Natural Language Inference1
Protein Structure Prediction1
Question Answering1
Safety Alignment1
Sentiment Analysis1
Specificity1
TAR1
Text Classification1
Word Sense Disambiguation1

Usage over time archive 2025-07-28

Papers per year tagged with Squared ReLU: 2021 to 2025, peak 3 3 0 2021: 3 papers 2021 2022: 3 papers 2022 2023: 3 papers 2023 2024: 3 papers 2024 2025: 3 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (15 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Activation Functions

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections