INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

tinyos

-0.63

enterOuterAlt

-0.62

 betweenstory

-0.59

oredCriteria

-0.56

XmlEnum

-0.54

 kohdetta

-0.53

-------------</

-0.51

featureID

-0.51

 Majefty

-0.51

setVerticalGroup

-0.50

POSITIVE LOGITS

�

0.69

�

0.68

 ��

0.43

����

0.40

��

0.40

וויק

0.38

jobId

0.38



0.37

 congi

0.36

 Witte

0.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.