INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

MigrationBuilder

-0.54

ThemeOverlay

-0.53

 chị

-0.51

 estimés

-0.50

beeren

-0.50

 puissent

-0.50

 appelez

-0.50

تقاوى

-0.49

XmlAccessorType

-0.47

Enllaces

-0.47

POSITIVE LOGITS

 disambiguazione

0.80

 jsPsych

0.75

bibinfo

0.62

UserScript

0.61

 Camilo

0.57

*/),

0.57

 Crusoe

0.55

الدراسه

0.55

 Smarty

0.55

 himſelf

0.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.