INDEX

Explanations

references to academic journals or publications

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

International Patent

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

parsedMessage

-0.71

UserScript

-0.67

TypedDataSet

-0.59

PerformLayout

-0.58

 getItemId

-0.58

GraphicsUnit

-0.57

ImageContext

-0.57

EndInit

-0.55

нгред

-0.55

最快更新

-0.54

POSITIVE LOGITS

Int

0.76

 International

0.67

Int

0.61

int

0.58

 international

0.52

International

0.51

int

0.48

 Intl

0.47

INT

0.46

 internal

0.45

Activations Density 0.003%

references to academic journals or publications

International Patent

No Comments

No Known Activations