INDEX

Explanations

numerical and data-related content

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

code fragments

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ViewImports

-0.70

 NSCoder

-0.68

DrawerToggle

-0.65

RenderAtEndOf

-0.60

OGND

-0.58

 CreateTagHelper

-0.55

setScene

-0.51

insegna

-0.51

 getItemId

-0.51

 portfolios

-0.51

POSITIVE LOGITS

 wireType

0.34

 linkovi

0.33

MathML

0.33

 المعيارى

0.32

obraz

0.32

normal

0.32

 հղումներ

0.31

 iprot

0.30

Merhaba

0.30

 empê

0.29

Activations Density 0.002%

numerical and data-related content

code fragments

No Comments

No Known Activations