INDEX

Explanations

references to scientific studies and their results, particularly in a medical or biological context

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

medical abbreviations and citations

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

 lenker

-0.54

richTextPanel

-0.53

HtmlAttribute

-0.49

#+#

-0.49

 שוליים

-0.48

AutoField

-0.47

 Italijanski

-0.46

<?

-0.46

󠁴

-0.46

 EClass

-0.46

POSITIVE LOGITS

COVID

0.47

Features

0.44

 COVID

0.44

boxShadow

0.42

±

0.42

 pylori

0.42

kiye

0.41

 Fitur

0.40

UpdatedAt

0.40

Activations Density 0.148%

references to scientific studies and their results, particularly in a medical or biological context

medical abbreviations and citations

No Comments

No Known Activations