INDEX

Explanations

references to events, shows, and industry-related terms

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

industry fairs and publications

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

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

 Paglinawan

-0.50

msgTypes

-0.48

 prisonniers

-0.48

AsUp

-0.48

 financière

-0.47

WebElementEntity

-0.47

 виправивши

-0.47

 expériment

-0.46

 '\\;'

-0.45

存于互联网档案馆

-0.45

POSITIVE LOGITS

✨:

0.41

#+#

0.40

Retail

0.38

ajinan

0.38

CloseOperation

0.38

 Retail

0.35

__*/

0.34

createCanvas

0.34

 spor

0.34

/******/

0.34

Activations Density 0.049%

references to events, shows, and industry-related terms

industry fairs and publications

No Comments

No Known Activations