INDEX

Explanations

programming and database-related syntax

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 @ 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

 bağlantılar

-0.36

 chi̍t

-0.36

 consultato

-0.36

ISupport

-0.35

 dimaksud

-0.32

 numberOfRows

-0.32

り返

-0.31

 analiz

-0.30

 pout

-0.30

 analyst

-0.29

POSITIVE LOGITS

 ContentValues

0.56

addCriterion

0.54

GIVEREF

0.54

ContentValues

0.51

setVerticalGroup

0.50

dAtA

0.49

BagConstraints

0.49

queryInterface

0.48

hObject

0.48

 الرياضيه

0.47

Activations Density 0.035%

programming and database-related syntax

code and technical terms

No Comments

No Known Activations