INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

SourceChecksum

-1.09

UserScript

-0.68

 صوتيه

-0.68

 مرئيه

-0.60

AndEndTag

-0.59

 تانيه

-0.57

 Réponses

-0.56

 للمعارف

-0.54

LookAnd

-0.52

 Bharat

-0.51

POSITIVE LOGITS

 mecánico

0.33

 gewöhnlich

0.32

paravant

0.32

 mecán

0.32

 Berücksich

0.28

including

0.27

trainable

0.27

 Zusammenhang

0.26

 antemano

0.26

inspace

0.26

Activations Density 0.000%

No Known Activations

This feature has no known activations.