INDEX

Explanations

references to specific geographical locations or areas

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

within followed by location

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

reportWebVitals

-0.39

webElementXpaths

-0.39

-0.37

 Atlántico

-0.35

########.

-0.35

 Navarra

-0.34

XmlAccessType

-0.34

Meta

-0.33

exports

-0.33

 meta

-0.33

POSITIVE LOGITS

 within

1.10

within

0.98

Within

0.94

 WITHIN

0.91

 Within

0.88

 innerhalb

0.81

 dentro

0.77

Dentro

0.76

dentro

0.73

 Dentro

0.72

Activations Density 0.016%

references to specific geographical locations or areas

within followed by location

No Comments

No Known Activations