INDEX

Explanations

entities and nouns related to names, brands, or products

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

Follows capitalized abbreviations or initials

np_acts-logits-general · gemini-2.0-flash

names of people and entities

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

 تضيفلها

-0.77

 referrerpolicy

-0.76

 autorytatywna

-0.64

Efq

-0.63

ChildScrollView

-0.59

">—

-0.59

mallow

-0.58

atshirt

-0.57

NUMX

-0.57

TintMode

-0.56

POSITIVE LOGITS

</strong>

0.58

LookAnd

0.58

</h3>

0.56

NKC

0.51

PropertyChanging

0.51

complexContent

0.48

 يتيمه

0.48

 gynhyrchwyd

0.45

 beginnetje

0.44

出版年

0.44

Activations Density 0.664%

entities and nouns related to names, brands, or products

Follows capitalized abbreviations or initials

names of people and entities

No Comments

No Known Activations