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

("")]

-0.49

 BrowserModule

-0.48

appBar

-0.48

'][]

-0.44

RTLI

-0.41

DispatchToProps

-0.40

glTexCoord

-0.38

🇺🇸

-0.37

 hole

-0.37

BrowserModule

-0.36

POSITIVE LOGITS

import

0.82

MessageOf

0.71

setVerticalGroup

0.64

MigrationBuilder

0.63

RenderAtEndOf

0.61

MessageTagHelper

0.59

دانشنامهٔ

0.58

 estekak

0.58

GOTREF

0.57

tanleria

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.