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

TestingModule

-0.59

 handleClick

-0.42

parseFrom

-0.41

 NgModule

-0.40

setObjectName

-0.39

 autorytatywna

-0.37

릎

-0.37

simpleType

-0.37

="_

-0.36

 hasNext

-0.36

POSITIVE LOGITS

\{\\

0.45

PullParser

0.45

höhung

0.42

ViewFeatures

0.41

 ويكيپيديا

0.39

Carrot

0.39

keith

0.39

 الرياضيه

0.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.