INDEX

Explanations

terms related to scientific or technical classifications and methodologies

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

after abbreviations or codes

np_acts-logits-general · gemini-2.0-flash

food items and technical terms

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

LabelTagHelper

-0.44

laravel

-0.43

杠

-0.41

zież

-0.41

 BitmapFactory

-0.40

litis

-0.40

didSet

-0.39

冬

-0.39

KeyListener

-0.39

槓

-0.38

POSITIVE LOGITS

بوابة

0.69

ngdoc

0.62

 onOptions

0.57

رشف

0.57

SequentialGroup

0.56

oredCriteria

0.55

DockStyle

0.54

 tabPage

0.53

Sharper

0.53

 BrowserModule

0.50

Activations Density 0.234%

terms related to scientific or technical classifications and methodologies

after abbreviations or codes

food items and technical terms

No Comments

No Known Activations