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

isOn

-0.36

 habet

-0.33

mes

-0.33

errores

-0.32

 loss

-0.32

fe

-0.31

 حم

-0.30

Pen

-0.30

έ

-0.30

たまた

-0.30

POSITIVE LOGITS

Mockito

4.53

 Mockito

1.85

IsMutable

0.80

Moq

0.80

 ویکی‌پدیا

0.75

omock

0.72

 AssemblyCompany

0.71

 Roskov

0.71

Javadoc

0.71

 ویکی‌پدیای

0.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.