INDEX

Explanations

marks or indicators related to biological or procedural references

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Non-English words or code

np_acts-logits-general · gemini-2.0-flash

scientific names and terms

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LookAnd

-0.69

abestanden

-0.66

 ***!

-0.59

bewerken

-0.56

UNIDENTIFIED

-0.55

</strong>

-0.54

شوند

-0.54

Upgrade

-0.53

 iNdEx

-0.53

ℕ

-0.52

POSITIVE LOGITS

 برانيه

0.94

__":

0.86

 referrerpolicy

0.86

__':

0.81

SpringBootTest

0.80

 autorytatywna

0.77

 tää

0.72

GOTREF

0.72

 ſtre

0.72

Efq

0.71

Activations Density 1.391%

marks or indicators related to biological or procedural references

Non-English words or code

scientific names and terms

No Comments

No Known Activations