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

 getItemCount

-1.31

IUrlHelper

-1.14

Previews

-1.03

LLocation

-0.60

HasAnnotation

-0.49

mycompany

-0.48

 igång

-0.31

 garaje

-0.30

ⓧ

-0.30

 AssemblyVersion

-0.30

POSITIVE LOGITS

MENAFN

3.41

uxxxx

1.00

出版年

0.92

GEBURTSDATUM

0.87

WebElementEntity

0.84

 betweenstory

0.81

BaseAdapter

0.77

firestore

0.73

 nahilalakip

0.72



0.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.