INDEX

Explanations

statements conveying seriousness or significance

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

signs and indications

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

oneofs

-0.56

 فريبيس

-0.56

сылкі

-0.56

 المعيارى

-0.54

esModule

-0.54

 виправивши

-0.54

DockStyle

-0.54

 kasarigan

-0.54

UnknownFieldSet

-0.53

onViewCreated

-0.52

POSITIVE LOGITS

 Einsch

0.33

utivos

0.31

//

0.29

 pozw

0.29

 muzik

0.28

 "..\..\

0.28

 level

0.28

выше

0.27

gól

0.27

pro

0.27

Activations Density 0.029%

statements conveying seriousness or significance

signs and indications

No Comments

No Known Activations