INDEX

Explanations

specific geographical locations or proper nouns

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

place names, people, and specific nouns

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

MENAFN

-0.56

!*\

-0.45

脚注の使い方

-0.45

 وتسجيلات

-0.43

 utafitiHapana

-0.43

 Rptr

-0.42

kháu

-0.42

󠁬

-0.42

ornment

-0.42

tagHelperRunner

-0.41

POSITIVE LOGITS

 kaarangay

0.45

 virksom

0.42

 clearColor

0.41

 Италијани

0.41

 aveug

0.40

 idéal

0.40

 verksamhet

0.39

 ekst

0.38

 TestBed

0.38

 étro

0.38

Activations Density 0.062%

specific geographical locations or proper nouns

place names, people, and specific nouns

No Comments

No Known Activations