INDEX

Explanations

specific programming and coding terms

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

file paths

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

-0.82

 AssemblyCulture

-0.71

 Италијани

-0.71

StructEnd

-0.62

UrlResolution

-0.58

webElementXpaths

-0.58

Personendaten

-0.57

GTCX

-0.57

 تضيفلها

-0.55

الدراسه

-0.54

POSITIVE LOGITS

 nonUne

0.49

abre

0.47

 Soccer

0.41

 basilica

0.41

Motif

0.41

 Edits

0.41

rar

0.41

 iner

0.40

sessions

0.40

cæ

0.40

Activations Density 0.044%

specific programming and coding terms

file paths

No Comments

No Known Activations