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

TextBoxColumn

-0.62

 HttpHeaders

-0.54

riwal

-0.50

angliski

-0.48

trane

-0.48

 columnIndex

-0.47

 sesama

-0.46

 StringTokenizer

-0.46

 betweenstory

-0.46

❹

-0.45

POSITIVE LOGITS

 build

0.67

 Build

0.65

 initComponents

0.60

enterOuterAlt

0.60

BuildContext

0.60

 createState

0.59

build

0.56

 builds

0.50

Build

0.49

 viewDidLoad

0.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.