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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WithIOException

-0.67

atshirt

-0.56

httphttps

-0.53

CVC

-0.53

BufferException

-0.51

 שוליים

-0.50

:✨

-0.50

JsonKey

-0.50

PPD

-0.49

withIdentifier

-0.48

POSITIVE LOGITS

ClientSize

0.80

 disambiguazione

0.54

 ویکی‌پدی

0.49

uxxxx

0.41

 męski

0.40

 całość

0.38

 cordones

0.35

 fallu

0.35

 jeunesse

0.35

 nocturna

0.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.