INDEX

Explanations

terminology related to medical protocols and laboratory procedures

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

FIL, HD, sky, LVM, US

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 kaarangay

-0.58

TypedDataSet

-0.48

oa̍t

-0.43

pushFollow

-0.42

rungsseite

-0.41

principalTable

-0.41

uvwxyz

-0.41

IntoConstraints

-0.41

withIdentifier

-0.40

 Italijanski

-0.40

POSITIVE LOGITS

 CreateTagHelper

0.64

vels

0.56

vets

0.56

viewDidLoad

0.55

vh

0.55

vl

0.55

vB

0.54

vc

0.54

veness

0.53

vP

0.53

Activations Density 0.099%

terminology related to medical protocols and laboratory procedures

FIL, HD, sky, LVM, US

No Comments

No Known Activations