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

SBATCH

-0.61

transQ

-0.56

 DataLoader

-0.53

vaadin

-0.53

SpringRunner

-0.53

 NgModule

-0.52

 balanceOf

-0.52

nipeg

-0.52

presto

-0.51

 UIFont

-0.51

POSITIVE LOGITS

 مشارکت‌کنندگان

4.63

 ویکی‌پدیا

0.83

دانشنامهٔ

0.78

 مشارکت

0.67

 Hivatalos

0.63

 ویکی‌پدیای

0.62

RenderAtEndOf

0.57

 nahilalakip

0.54

hyrchwyd

0.50

‌کنندگان

0.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.