INDEX

Explanations

phrases related to medical treatment indications and regulatory approvals

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

Text after URLs or formal/official wording

np_acts-logits-general · gemini-2.0-flash

foreign language and programming terms

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

انجليز

-0.52

 surla

-0.50

varlak

-0.50

 Töchter

-0.49

tizens

-0.47

]")]

-0.46

addContainerGap

-0.44

guiente

-0.43

 itinéraires

-0.43

 siebie

-0.43

POSITIVE LOGITS

 beginnetje

0.46

ViewImports

0.39

PerformLayout

0.39

Autoritní

0.38

 мәкал

0.34

waitKey

0.34

 Италијани

0.34

 المعيارى

0.33

 California

0.33

antMatchers

0.32

Activations Density 0.244%

phrases related to medical treatment indications and regulatory approvals

Text after URLs or formal/official wording

foreign language and programming terms

No Comments

No Known Activations