INDEX

Explanations

No Explanations Found

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

WillAppear

-0.49

 تضيفلها

-0.43

 naturels

-0.42

 présidenti

-0.41

 religieux

-0.41

ResumeLayout

-0.40

 immobilier

-0.40

 Segurança

-0.40

 Isto

-0.40

CrossRef

-0.40

POSITIVE LOGITS

ftagPool

0.74

TagMode

0.54

 المعيارى

0.50

adaptiveStyles

0.45

:✨

0.45

 Wikimedijinoj

0.45

__',

0.45

اریخ

0.44

Cyfarwyddwr

0.44

opers

0.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.