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

queles

-0.35

 Leistungen

-0.32

 Outros

-0.29

ghest

-0.28

 Otros

-0.28

 Begründung

-0.27

 laikā

-0.27

 ModelRenderer

-0.27

knex

-0.27

 Züge

-0.26

POSITIVE LOGITS

appcompat

3.92

 AppCompat

1.13

 autorytatywna

1.09

AppCompat

1.08

ChildScrollView

1.04

 defaultstate

1.02

CppMethod

0.94

 للاسماء

0.91

 незавершена

0.90

 informée

0.89

Activations Density 0.000%

No Known Activations

This feature has no known activations.