INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Dud

-0.78

 initWithFrame

-0.77

脚注の使い方

-0.69

numerusform

-0.66

Dud

-0.64

 cessation

-0.62

HIP

-0.61

leicht

-0.60

ArgumentParser

-0.60

 Cess

-0.60

POSITIVE LOGITS

Искәрмәләр

0.68

AuthContext

0.65

 مرئيه

0.64

Collegamenti

0.62

 educativas

0.58

 initComponents

0.57

 mẽ

0.56

 financieras

0.56

alumni

0.54

ersoll

0.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.