INDEX

Explanations

specific HTML or programming attributes and related function names

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

valign="

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

AccessorTable

-0.50

findpost

-0.47

mbic

-0.46

rawDesc

-0.46

fjspx

-0.45

kalan

-0.45

Personensuche

-0.45

WithIOException

-0.45

DropTable

-0.45

getMenuInflater

-0.45

POSITIVE LOGITS

HasColumnName

0.92

datable

0.71

subplot

0.64

 getView

0.60

 valign

0.57

ReusableCell

0.56

 FetchType

0.55

existsSync

0.55

strokeStyle

0.53

 ViewPager

0.52

Activations Density 0.001%

specific HTML or programming attributes and related function names

valign="

No Comments

No Known Activations

specific HTML or programming attributes and related function names

valign="

No Comments

No Known Activations