INDEX

Explanations

medical terminology related to diagnoses and treatments

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

medical conditions and findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

UserScript

-0.66

LabelTagHelper

-0.64

 ModelExpression

-0.64

\{\\

-0.63

########.

-0.62

+#+#

-0.58

setupUi

-0.54

Diweddarwch

-0.54

Vidite

-0.52

hicles

-0.51

POSITIVE LOGITS

 moderate

0.58

 mixed

0.55

 diffuse

0.54

 moderately

0.50

 mild

0.48

moderate

0.47

 Mixed

0.46

 mildly

0.45

diffuse

0.44

mixed

0.44

Activations Density 0.305%

medical terminology related to diagnoses and treatments

medical conditions and findings

No Comments

No Known Activations