INDEX

Explanations

words or phrases related to specific scientific concepts, particularly in fields like physics and materials science

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

Code, technical jargon, or symbols

np_acts-logits-general · gemini-2.0-flash

names followed by text

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

enterOuterAlt

-0.60

 disambiguazione

-0.60

Obrázky

-0.55

 ***!

-0.53

 gyhoeddwyd

-0.52

and

-0.51

 recensement

-0.51

komsten

-0.50

}}}

-0.49

 يتيمه

-0.48

POSITIVE LOGITS

 alike

1.00

 Мексичка

0.70

EnableWeb

0.65

OrBuilder

0.64

etc

0.60

ETC

0.60

toHaveBeenCalled

0.58

 nakalista

0.58

 שוליים

0.57

 Exacts

0.57

Activations Density 0.555%

words or phrases related to specific scientific concepts, particularly in fields like physics and materials science

Code, technical jargon, or symbols

names followed by text

No Comments

No Known Activations