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

Portail

-0.38

destroyAll

-0.36

 zvuky

-0.35

الحياه

-0.35

Subview

-0.35

pu

-0.34

 underground

-0.31

illoma

-0.31

}{-

-0.31

fillType

-0.31

POSITIVE LOGITS

 MediatR

5.00

ngrx

0.96

 AutoMapper

0.94

DataAnnotations

0.85

 ProtoMessage

0.74

Mediator

0.71

mediator

0.68

 Mediator

0.66

protoimpl

0.65

 createSlice

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.