INDEX

Explanations

elements related to numerical data or measurements

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

international characters and numbers

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

rungsseite

-0.50

 يتيمه

-0.50

liceerd

-0.46

astify

-0.42



-0.41

domada

-0.39

 CreateTagHelper

-0.39

脚注の使い方

-0.39

 ceinture

-0.38

Souls

-0.38

POSITIVE LOGITS

 nakalista

0.56

Jeografia

0.50

 PeEnEo

0.49

IUrlHelper

0.46

tvguidetime

0.39

Наводи

0.38

ьажоргаш

0.38

jspb

0.37

//

0.36

Autoritní

0.35

Activations Density 0.254%

elements related to numerical data or measurements

international characters and numbers

No Comments

No Known Activations