INDEX

Explanations

words related to scientific testing and evaluation

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

preceding names or locations

np_acts-logits-general · gemini-2.0-flash

foreign words

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

IsMutable

-0.79

///</

-0.70

EDEFAULT

-0.69

 CreateTagHelper

-0.69

DebuggerNonUser

-0.68

LookAnd

-0.65

Geplaatst

-0.62

ApiModelProperty

-0.62

 disambiguazione

-0.61

 >=",

-0.59

POSITIVE LOGITS

 mourut

0.59

 levure

0.56

 actualité

0.53

 asiatique

0.51

ientôt

0.49

Nuorodos

0.49

 kuni

0.48

Viungo

0.48

 referentes

0.47

 Ähnliche

0.47

Activations Density 0.612%

words related to scientific testing and evaluation

preceding names or locations

foreign words

No Comments

No Known Activations