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

setVerticalGroup

-0.86

 betweenstory

-0.85

 Numerade

-0.81

Tembelea

-0.78

 CreateTagHelper

-0.76

RegressionTest

-0.76

 indígen

-0.75

ágenes

-0.75

CloseOperation

-0.72

rungsseite

-0.72

POSITIVE LOGITS

The

0.58

<bos>

0.49

Pal

0.46

Mac

0.45

the

0.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.