INDEX

Explanations

instances of strong emphasis or significance

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

emphasis or section markers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 saveiro

-0.79

 ddelwed

-0.66

 niedersachsen

-0.65

nezeu

-0.65

createCanvas

-0.63

şört

-0.63

 increí

-0.62

 Italijani

-0.62

 kapture

-0.61

ſammen

-0.61

POSITIVE LOGITS

0.55

awtextra

0.49

>-</

0.47

*-

0.46

•

0.46

0.45

hline

0.44

•

0.44

*\

0.44

0.42

Activations Density 0.000%

instances of strong emphasis or significance

emphasis or section markers

No Comments

No Known Activations