INDEX

Explanations

specific dates and events related to incidents or notable occurrences

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

dates and numbers

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

enterOuterAlt

-0.41

RenderAtEndOf

-0.40

inWeight

-0.37

grès

-0.37

pond

-0.36

 Sélectionnez

-0.36

UnusedPrivate

-0.35

 Baxter

-0.35

StructEnd

-0.35

effort

-0.35

POSITIVE LOGITS

 للمعارف

0.56

GEBURTSDATUM

0.54

ंदीखरीदारी

0.54

⟬

0.54

+#+#

0.53

AntiForgeryToken

0.51

LOYEES

0.50

ніципа

0.50

PMailer

0.50

 beginnetje

0.48

Activations Density 0.037%

specific dates and events related to incidents or notable occurrences

dates and numbers

No Comments

No Known Activations