INDEX

Explanations

phrases and terms related to the act of learning or gaining knowledge

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

learn more

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

retudo

-0.50

那種

-0.48

 orçamento

-0.42

Personensuche

-0.42

Firstly

-0.41

 resourceCulture

-0.40

elux

-0.40

Damit

-0.40

 ته

-0.40

ConstraintMaker

-0.39

POSITIVE LOGITS

 learn

0.97

 Learn

0.85

Learn

0.85

learn

0.83

 LEARN

0.81

LEARN

0.77

 learned

0.70

 learns

0.70

Autoritní

0.65

 learning

0.63

Activations Density 0.010%

phrases and terms related to the act of learning or gaining knowledge

learn more

No Comments

No Known Activations