INDEX

Explanations

specific names and numerical identifiers related to scientific and legal contexts

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

names and non-latin characters

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

 Stur

-0.55

toria

-0.52

Schw

-0.51

JMenuBar

-0.51

rius

-0.50

''''

-0.50

 Schw

-0.50

 Maur

-0.49

NameInMap

-0.49

Chou

-0.48

POSITIVE LOGITS

InputModule

0.56

 Komunikasi

0.52

 referrerpolicy

0.51

FEC

0.50

 Filosof

0.49

 toledo

0.47

 Budaya

0.47

 Toledo

0.47

ibatkan

0.47

 Ilustra

0.47

Activations Density 0.553%

specific names and numerical identifiers related to scientific and legal contexts

names and non-latin characters

No Comments

No Known Activations