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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

+#+#

-0.63

MessageOf

-0.60

ngrx

-0.60

 nonUne

-0.60

 betweenstory

-0.59

TextBoxColumn

-0.58

RegressionTest

-0.58

]=>

-0.56

MockBean

-0.55

featureID

-0.54

POSITIVE LOGITS

IContainer

0.36

 فريبيس

0.36

complexContent

0.33

 stof

0.32

jarse

0.32

hyrchwyd

0.31

 biochemistry

0.31

BuildContext

0.30

 informée

0.30

 React

0.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.