INDEX

Explanations

terms related to clinical studies and practices

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

clinical applications

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

way

-0.56

 eğer

-0.54

 Potencia

-0.52

 Hälfte

-0.51

Ventajas

-0.50

 députés

-0.49

 sauce

-0.49

 indietro

-0.49

เติม

-0.48

rdı

-0.47

POSITIVE LOGITS

Clinical

0.86

 Clinical

0.82

clinical

0.80

 CLINICAL

0.79

 clinical

0.78

CLINICAL

0.71

Clin

0.66

 Clin

0.60

Clinic

0.60

FXML

0.59

Activations Density 0.026%

terms related to clinical studies and practices

clinical applications

No Comments

No Known Activations