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

 ſche

-0.75

ScopeManager

-0.64

ſelves

-0.60

 Favre

-0.60

 pleaſure

-0.60

typeparam

-0.59

 deleteUser

-0.59

pthread

-0.58

 pthread

-0.57

Nathalie

-0.57

POSITIVE LOGITS

is

1.30

Is

0.99

is

0.97

Is

0.94

are

0.79

IS

0.77

has

0.71

was

0.63

は

0.59

è

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.