INDEX

Explanations

numerical data related to health metrics or measurements

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

the number 0

np_acts-logits-general · gemini-2.0-flash

multilingual technical terms

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

“

-0.62

↵↵

-0.55

-0.53

-0.52

si

-0.50

候

-0.50

«

-0.49

-0.48

POSITIVE LOGITS

脚注の使い方

1.31

ConstraintMaker

1.28

ंदीखरीदारी

1.26

 مشين

1.24

 utafitiHapana

1.20

 المعيارى

1.19

InjectAttribute

1.18

AndEndTag

1.18

 فريبيس

1.18

Efq

1.17

Activations Density 0.641%

numerical data related to health metrics or measurements

the number 0

multilingual technical terms

No Comments

No Known Activations