INDEX

Explanations

data structure indicators or formatting symbols

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

Numbers followed by other numbers

np_acts-logits-general · gemini-2.0-flash

code snippets and symbols

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

ly

-0.95

ting

-0.83

ً

-0.79

FXML

-0.77

MOUTH

-0.73

gdx

-0.71

mente

-0.70

тно

-0.70

bly

-0.69

zuma

-0.68

POSITIVE LOGITS

קישורים

0.88

ypsies

0.74

 Danilo

0.69

PAH

0.68

к

0.66

 Galilee

0.66

PYX

0.65

0.64

 sasuke

0.64

 Phry

0.63

Activations Density 0.337%

data structure indicators or formatting symbols

Numbers followed by other numbers

code snippets and symbols

No Comments

No Known Activations