INDEX

Explanations

keywords related to programming and data types in a coding context

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

"repeated" or "optional" followed by a data type

np_acts-logits-general · gemini-2.0-flash

packed repeated optional fields

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TestingModule

-0.55

ülé

-0.46

 corona

-0.44

anderen

-0.39

 הה

-0.39

انه

-0.39

Mr

-0.39

 huom

-0.39

ternal

-0.38

 بالت

-0.38

POSITIVE LOGITS

 float

1.23

float

1.10

 Float

1.03

 floats

1.03

 double

1.00

 integer

0.95

Float

0.95

 doubles

0.93

double

0.91

doubles

0.90

Activations Density 0.932%

keywords related to programming and data types in a coding context

"repeated" or "optional" followed by a data type

packed repeated optional fields

No Comments

No Known Activations