INDEX

Explanations

names of villages and geographical locations

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

populated places

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

تقاوى

-0.58

endregion

-0.46

 Roskov

-0.44

 ویکی‌پدی

-0.44

 dAtA

-0.43

fjspx

-0.42

 فريبيس

-0.41

 versions

-0.39

 kaarangay

-0.39

 definitions

-0.38

POSITIVE LOGITS

wieś

0.58

Personensuche

0.48

Ƚ

0.45

parsedMessage

0.44

fauna

0.43

inWeight

0.43

 nameof

0.42

Adults

0.42

 Specialists

0.42

desertcart

0.42

Activations Density 0.008%

names of villages and geographical locations

populated places

No Comments

No Known Activations