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

me

-0.28

లాలు

-0.24

Fab

-0.23

 crawl

-0.22

 fact

-0.22

 period

-0.22

fab

-0.21

 wrap

-0.21

(),

-0.21

pha

-0.21

POSITIVE LOGITS

IndentedString

0.76

 GenerationType

0.73

transQ

0.72

guisement

0.69

 незавершена

0.69

 queſta

0.67

OGND

0.65

UserScript

0.65

VersionUID

0.63

 Wikispecies

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.