INDEX

Explanations

specific brands or company names related to technology and media

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

Illumina Inc

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

 myſelf

-0.56

Efq

-0.55

 Diſ

-0.54

 Monfieur

-0.53

ſelf

-0.52

 itſelf

-0.50

 Perſ

-0.47

Eſ

-0.47

APORE

-0.46

 colgantes

-0.46

POSITIVE LOGITS

MENAFN

0.76

ymce

0.65

 Picchu

0.57

 Numerade

0.54

 Schengen

0.53

LookAnd

0.52

 defaultstate

0.52

 informée

0.50

httphttps

0.49

aliana

0.48

Activations Density 0.005%

specific brands or company names related to technology and media

Illumina Inc

No Comments

No Known Activations