INDEX

Explanations

references to models or frameworks including abbreviations and formal titles

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

Abbreviations in parentheses

np_acts-logits-general · gemini-2.0-flash

abbreviations and acronyms

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 preghiera

-0.45

 scolaires

-0.43

NullException

-0.42

 AssemblyCulture

-0.41

 précédents

-0.41

 culturelles

-0.41

apiUrl

-0.40

 médicaux

-0.39

 religieuses

-0.39

 généraux

-0.39

POSITIVE LOGITS

DS

1.27

FS

1.22

BS

1.20

FS

1.20

GS

1.20

CS

1.19

GS

1.19

DS

1.16

PS

1.15

QS

1.14

Activations Density 0.451%

references to models or frameworks including abbreviations and formal titles

Abbreviations in parentheses

abbreviations and acronyms

No Comments

No Known Activations