INDEX

Explanations

mathematical and scientific notation or terminology

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

LaTeX math mode delimiters ("_" or ",")

np_acts-logits-general · gemini-2.0-flash

indices and mathematical notation

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

TER

-0.55

Baz

-0.50

ter

-0.50

фы

-0.49

Ter

-0.49

 onCreateView

-0.49

 québéco

-0.48

Baz

-0.48

IZ

-0.48

USS

-0.43

POSITIVE LOGITS

enumi

0.78

ImageContext

0.75

AsUp

0.72

ToScroll

0.71

InSection

0.71

 AssemblyCulture

0.70

SharedDtor

0.69

UrlResolution

0.67

 جغرافيا

0.67

IsMutable

0.67

Activations Density 1.079%

mathematical and scientific notation or terminology

LaTeX math mode delimiters ("_" or ",")

indices and mathematical notation

No Comments

No Known Activations