INDEX

Explanations

numerical data or statistical results

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

numerals and section markers

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

tvguidetime

-0.55

CloseOperation

-0.53

 UIImageView

-0.49

__":

-0.48

 BrowserModule

-0.48

SBATCH

-0.47

XmlAccessorType

-0.46



-0.45

lccn

-0.45

DrawerToggle

-0.44

POSITIVE LOGITS

rungsseite

0.45

ViewFeatures

0.41

verwijspagina

0.38

"}";

0.38

PONENTS

0.38

 препратки

0.38

 Haftung

0.36

WillAppear

0.35

 baskılı

0.35

 médicale

0.35

Activations Density 0.079%

numerical data or statistical results

numerals and section markers

No Comments

No Known Activations