INDEX

Explanations

references to capabilities and functionalities of technology systems

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

ability allows

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

Garantía

-0.37

 nastav

-0.35

unregister

-0.34

 trial

-0.32

 Haushalt

-0.32

 sold

-0.31

 doğum

-0.30

 nedenle

-0.30

NullCheck

-0.29

–

-0.29

POSITIVE LOGITS

 للمعارف

0.80

 disambiguazione

0.72

httphttps

0.72

 rospy

0.62

 MainAxisSize

0.60

WithIOException

0.60

DeleteBehavior

0.60

tvguidetime

0.59

AsUp

0.59

rungsseite

0.59

Activations Density 0.608%

references to capabilities and functionalities of technology systems

ability allows

No Comments

No Known Activations