INDEX

Explanations

connections to disease names and specific medical conditions

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

listing with and

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

 thing

-0.41

aarrggbb

-0.41

 UITableViewCell

-0.41

ActionResult

-0.40

 <>",

-0.40

umumkan

-0.39

 Frankel

-0.39

ится

-0.37

来歴

-0.36

 together

-0.36

POSITIVE LOGITS

 ligiloj

0.53

PerformLayout

0.49

ViewFeatures

0.47

󠁣

0.45

 maupun

0.45

ValueStyle

0.43

 للمعارف

0.42

MathML

0.41

 Versions

0.40

pecially

0.40

Activations Density 0.092%

connections to disease names and specific medical conditions

listing with and

No Comments

No Known Activations