INDEX

Explanations

medical terms and classifications related to tumors and their characteristics

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

Percentages within parentheses

np_acts-logits-general · gemini-2.0-flash

percentages and fractions

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

 Ninety

-0.46

RenderAtEndOf

-0.46

posedge

-0.45

 thousand

-0.43

 billions

-0.43

 majority

-0.42

urb

-0.42

 exceed

-0.41

 domin

-0.41

POSITIVE LOGITS

poptosis

0.71

 saites

0.69

mentaire

0.65

ImageContext

0.65

 للاسماء

0.62

 suivantes

0.62

AnimationsModule

0.60

itarias

0.60

\{\\

0.59

참고

0.59

Activations Density 0.393%

medical terms and classifications related to tumors and their characteristics

Percentages within parentheses

percentages and fractions

No Comments

No Known Activations