INDEX

Explanations

references to scientific concepts and terms

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

"β-actin" or "β tubulin"

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

脚注の使い方

-0.67

 الحره

-0.57

Viitteet

-0.55

ArgsConstructor

-0.53

 ExecuteAsync

-0.44

期刊论文

-0.42

MLLoader

-0.42

ISTIC

-0.41

KommentareTeilen

-0.40

 CreateTagHelper

-0.40

POSITIVE LOGITS

WebServlet

0.50

chromedriver

0.40

Diwedd

0.40

.*")]

0.39

chtenstein

0.39

 ویکی‌پدی

0.38

 MaterialApp

0.38

 рее

0.38

 IActionResult

0.38

 CommonModule

0.38

Activations Density 0.084%

references to scientific concepts and terms

"β-actin" or "β tubulin"

No Comments

No Known Activations