INDEX

Explanations

phrases related to availability and options

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

available

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

 definition

-0.40

Portail

-0.38

uminen

-0.38

 Schleswig

-0.38

 itself

-0.38

 Henn

-0.37

 strlen

-0.36

《

-0.36

OuterClass

-0.36

'{@

-0.36

POSITIVE LOGITS

esModule

0.60

 mož

0.51

 GenerationType

0.50

 možnost

0.50

 gegebenen

0.49

 אפשר

0.48

fxml

0.48

HasAnnotation

0.48

 possibilité

0.48

 disponible

0.47

Activations Density 0.013%

phrases related to availability and options

available

No Comments

No Known Activations