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

 betweenstory

-0.48

NOSIS

-0.37

nasium

-0.34

Affiliations

-0.32

 terminal

-0.31

 paille

-0.30

terminal

-0.30

こんにちは

-0.30

skj

-0.30

IntoConstraints

-0.29

POSITIVE LOGITS

tagHelperRunner

0.76

WebVitals

0.69

rafa

0.62

 noDo

0.61

OGND

0.60

istoitu

0.60

 nahilalakip

0.60

出版年

0.60

 kasarigan

0.58

Coordenadas

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.