INDEX

Explanations

numerical data and expressions of estimated values

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

Exponentials and plus/minus signs

np_acts-logits-general · gemini-2.0-flash

scientific notation & symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

чин

-0.54

 legislation

-0.45

boxShadow

-0.43

硃

-0.41

opc

-0.40

 şek

-0.39

 mesi

-0.39

 náv

-0.39

шна

-0.39

POSITIVE LOGITS

IntoConstraints

0.99

ंदीखरीदारी

0.90

 يتيمه

0.88

UnusedPrivate

0.86

providedIn

0.83

usermodel

0.81

Datuak

0.80

存于互联网档案馆

0.80

+:+

0.77

 MotionEvent

0.77

Activations Density 0.303%

numerical data and expressions of estimated values

Exponentials and plus/minus signs

scientific notation & symbols

No Comments

No Known Activations