INDEX

Explanations

references to specific machine learning libraries and frameworks

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

Python libraries

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

SourceChecksum

-1.23

 nahilalakip

-1.09

 &___

-1.05

IVEREF

-1.00

InjectAttribute

-1.00

 kaarangay

-0.99

 المعيارى

-0.98

RenderAtEndOf

-0.97

下载附件

-0.97

 تضيفلها

-0.97

POSITIVE LOGITS

 sklearn

1.91

 scipy

0.70

 skimage

0.63

reactivex

0.48

0.46

 elegans

0.44

’

0.43

vereins

0.43

 Völker

0.43

Vgl

0.43

Activations Density 0.006%

references to specific machine learning libraries and frameworks

Python libraries

No Comments

No Known Activations