INDEX

Explanations

geographical locations and related terms

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

countries and regions

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

 ujednoznacz

-0.52

+#+#

-0.52

<?

-0.49

 kader

-0.48

MLLoader

-0.47

 незавершена

-0.46

Personensuche

-0.46

เห

-0.46

ByVersion

-0.46

 marinho

-0.46

POSITIVE LOGITS

setVerticalGroup

0.40

تفصیلات

0.40

iann

0.36

isand

0.36

upol

0.35

IMDG

0.35

 Slaves

0.35

akei

0.33

uits

0.32

ans

0.32

Activations Density 0.021%

geographical locations and related terms

countries and regions

No Comments

No Known Activations