INDEX

Explanations

prominent names, numbers, and code snippets

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

prime factors

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

contentLoaded

-0.66

twimg

-0.56

 Administrativna

-0.56

Manbalar

-0.55

IsMutable

-0.54

webElementXpaths

-0.53

 CreateTagHelper

-0.52

 Italijani

-0.52

Jîn

-0.52

 lenker

-0.51

POSITIVE LOGITS

Fos

0.42

sune

0.42

rons

0.42

 Banners

0.42

 Flag

0.40

findpost

0.39

Flags

0.39

rona

0.39

zuk

0.39

PMA

0.38

Activations Density 0.275%

prominent names, numbers, and code snippets

prime factors

No Comments

No Known Activations