INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 estekak

-0.44

पया

-0.41

estacks

-0.41

 препратки

-0.40

 ligiloj

-0.39

RenderAtEndOf

-0.38

 فريبيس

-0.38

pexpr

-0.37

 podjela

-0.36

transQ

-0.36

POSITIVE LOGITS

به

2.08

بة

0.76

 به

0.69

 به‌

0.57

وبه

0.57

HostException

0.55

Vegeu

0.52

ExtendWith

0.51

onViewCreated

0.48

ⓧ

0.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.