INDEX

Explanations

numerical values and scientific notation indicators

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

Mathematical or scientific notation

np_acts-logits-general · gemini-2.0-flash

medical journals 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

Hauptartikel

-0.70

 pinulongan

-0.69

WriteTagHelper

-0.68

DBNull

-0.66

 ligiloj

-0.64

�

-0.63

 BoxDecoration

-0.63

abestanden

-0.62

KommentareTeilen

-0.59

 OnInit

-0.58

POSITIVE LOGITS

 nephe

0.60

 synag

0.59

 pediatrician

0.56

 Sarm

0.55

 gneiss

0.55

 Nantucket

0.55

 bellows

0.54

 custard

0.54

 dreamstime

0.53

ufe

0.53

Activations Density 0.084%

numerical values and scientific notation indicators

Mathematical or scientific notation

medical journals and entities

No Comments

No Known Activations