INDEX

Explanations

structured data and references

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

Numbers and symbols in text

np_acts-logits-general · gemini-2.0-flash

`isdigit . isdigit`

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iNdEx

-0.65

HasAnnotation

-0.60

RegistryLite

-0.59

 volto

-0.58

 Himo

-0.58

 tendances

-0.58

RegressionTest

-0.57

 bianchi

-0.56

EDEFAULT

-0.56

awaiter

-0.56

POSITIVE LOGITS

országban

0.58

Tracce

0.57

MLLoader

0.51

例文帳に追加

0.47

Pozri

0.47

'];?>

0.45

écial

0.45

0.43

躇

0.43

 }}"></

0.43

Activations Density 0.245%

structured data and references

Numbers and symbols in text

`isdigit . isdigit`

No Comments

No Known Activations