INDEX

Explanations

scenes and references in narrative contexts

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

"Scene" or "Scenes"

np_acts-logits-general · gemini-2.0-flash

scene recognition or scene graph

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

RetentionPolicy

-0.71

multer

-0.69

ostante

-0.66

üyük

-0.65

antMatchers

-0.63

rusted

-0.63

úgó

-0.63

 extensible

-0.61

 strane

-0.60

 podjela

-0.59

POSITIVE LOGITS

 scene

1.86

 scenes

1.85

 SCENE

1.77

 Scene

1.71

 Scenes

1.62

scene

1.60

SCENE

1.55

Scenes

1.43

SceneManagement

1.43

Scene

1.42

Activations Density 0.120%

scenes and references in narrative contexts

"Scene" or "Scenes"

scene recognition or scene graph

No Comments

No Known Activations