INDEX

Explanations

coding syntax or formatting markers

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

code/latex section starts

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

 disambiguazione

-1.00

GEBURTS

-0.88

 Administrativna

-0.81

 queſta

-0.79

AndEndTag

-0.79

Personendaten

-0.77

 surla

-0.77

 Italijani

-0.76

niſſe

-0.76

bootstrapcdn

-0.75

POSITIVE LOGITS

ada

0.31

frage

0.30

 Beginning

0.29

 beginning

0.28

 begun

0.28

query

0.27

everything

0.26

里

0.25

Everything

0.25

始

0.25

Activations Density 0.001%

coding syntax or formatting markers

code/latex section starts

No Comments

No Known Activations