INDEX

Explanations

references to spokespersons and their statements

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

spokesman or spokeswoman statements

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

 Савезне

-0.63

новниш

-0.61

Vidite

-0.56

 समीक्षक

-0.55

 BoxFit

-0.54

UnusedPrivate

-0.50

Abp

-0.49

windowFixed

-0.49

évaluateur

-0.48

ParallelGroup

-0.48

POSITIVE LOGITS

contentLoaded

0.36

wakili

0.34

JdbcTemplate

0.33

 negar

0.33

épendance

0.32

 tieto

0.32

 admitir

0.32

ungkinkan

0.32

vivencia

0.32

 estatu

0.30

Activations Density 0.010%

references to spokespersons and their statements

spokesman or spokeswoman statements

No Comments

No Known Activations