INDEX

Explanations

names of institutions and grant supporters

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

Followed by an organization or institute

np_acts-logits-general · gemini-2.0-flash

research institutions and funding

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

VersionUID

-0.79

 mold

-0.67

TintMode

-0.65

StoreMessageInfo

-0.64

InputBorder

-0.62

 molds

-0.62

 labors

-0.61

 Wicidata

-0.61

 /\.(

-0.60

TagMode

-0.60

POSITIVE LOGITS

 recognise

0.55

 recognised

0.53

 recognises

0.51

 summarised

0.50

 beliau

0.49

UK

0.49

DeleteBehavior

0.48

 recognising

0.48

UK

0.47

 bahawa

0.47

Activations Density 0.220%

names of institutions and grant supporters

Followed by an organization or institute

research institutions and funding

No Comments

No Known Activations