INDEX

Explanations

scientific or academic references and citations

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

academic references and citations

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

createClass

-0.37

Cor

-0.36

 Bron

-0.33

cor

-0.31

 favour

-0.31

 kerajaan

-0.30

 Elder

-0.30

cor

-0.30

Cor

-0.30

Coordonnées

-0.29

POSITIVE LOGITS

GOTREF

0.59

évaluateur

0.56

 Chwiliwch

0.56

 ब्रेकडाउन

0.53

tagHelperRunner

0.53

IBOutlet

0.52

 utafitiHapana

0.50

astify

0.50

AddTagHelper

0.49

 للمعارف

0.48

Activations Density 0.117%

scientific or academic references and citations

academic references and citations

No Comments

No Known Activations