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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 MainAxisSize

-1.23

Tembelea

-0.65

 تضيفلها

-0.60

 للمعارف

-0.58

出版年

-0.50

mobileqq

-0.50

abestanden

-0.49

 BorderSide

-0.48

 EconPapers

-0.48

'{@

-0.47

POSITIVE LOGITS

Попис

0.60

UniformLocation

0.39

exitRule

0.38

צות

0.36

UPPER

0.36

 Wilkinson

0.35

 True

0.35

rawDesc

0.35

JspWriter

0.35

An

0.34

Activations Density 0.000%

No Known Activations

This feature has no known activations.