INDEX

Explanations

phrases and terms related to language translation and localization

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

language identifiers and common web terms

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ագրություններ

-0.60

StoryboardSegue

-0.55

ViewFeatures

-0.55

SharedDtor

-0.54

ValueGenerated

-0.53

@"/

-0.53

GEBURTSDATUM

-0.52

 calendriers

-0.52

UIControlState

-0.50

ſſung

-0.49

POSITIVE LOGITS

XmlAccessType

0.34

नलिखित

0.32

 maternelle

0.32

AnimationsModule

0.31

ViewImports

0.31

optionalTypeArgs

0.31

SourceChecksum

0.31

ölkerung

0.30

 lizenzfreie

0.30

tagHelperRunner

0.30

Activations Density 0.017%

phrases and terms related to language translation and localization

language identifiers and common web terms

No Comments

No Known Activations