INDEX

Explanations

names and terms related to scientific fields and institutions

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

clinical trial

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

CloseOperation

-0.45

Chham

-0.45

 deadliest

-0.43

 externi

-0.42

engeance

-0.40

 disarm

-0.40

 clemen

-0.39

labus

-0.39

 Goliath

-0.39

生死

-0.38

POSITIVE LOGITS

KommentareTeilen

0.67

 fédé

0.58

 réuss

0.56

EDEFAULT

0.56

fillType

0.53

erçe

0.53

 réus

0.52

 NSMutable

0.52

 réussir

0.51

 grecque

0.49

Activations Density 0.190%

names and terms related to scientific fields and institutions

clinical trial

No Comments

No Known Activations