INDEX

Explanations

mathematical symbols and notations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

formatting for code and math

np_acts-logits-general · gemini-2.5-flash-lite

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

 فريبيس

-0.72

setViewportView

-0.53

 CreateTagHelper

-0.48

AddTagHelper

-0.48

AccessorTable

-0.47

 tartalomajánló

-0.46

 الاطلاع

-0.46

 تضيفلها

-0.44

iſten

-0.44

 مشارکت‌کنندگان

-0.44

POSITIVE LOGITS

+#+#

0.63

getJSONArray

0.45

**********/

0.43

reszcie

0.41

⤹

0.41

 Biôgrafia

0.40

 loisirs

0.39

 bambú

0.38

wakilan

0.37

 joão

0.37

Activations Density 0.407%

mathematical symbols and notations

formatting for code and math

No Comments

No Known Activations