INDEX

Explanations

specific numerical or mathematical expressions

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

code and technical terms

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tvguidetime

-0.57

 useAppContext

-0.50

 الحره

-0.50

AZINE

-0.47

 للمعارف

-0.46

WebServlet

-0.46

Wart

-0.45

页面存档备份

-0.45

writerow

-0.44

$_"

-0.43

POSITIVE LOGITS

↹

0.41

XtraReports

0.40

hoeddwyd

0.40

 propOrder

0.39

 незавершена

0.38

CloseOperation

0.37

󠁴

0.37

webElementXpaths

0.36

탤

0.36

/**

0.36

Activations Density 0.000%

specific numerical or mathematical expressions

code and technical terms

No Comments

No Known Activations