INDEX

Explanations

proper nouns and character names in historical or mythological contexts

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

proper names and programming terms

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

 performance

-0.36

 performances

-0.33

parseFloat

-0.32

 faixa

-0.29

 disposição

-0.29

performance

-0.29

 graça

-0.28

中

-0.28

roj

-0.28

 combinations

-0.28

POSITIVE LOGITS

 المعيارى

0.89

 CreateTagHelper

0.75

 estekak

0.74

IsContent

0.70

 Administrativna

0.68

richTextPanel

0.66

formik

0.64

 الحره

0.64

EDEFAULT

0.64

ScopeManager

0.63

Activations Density 0.033%

proper nouns and character names in historical or mythological contexts

proper names and programming terms

No Comments

No Known Activations