INDEX

Explanations

scientific terms and statistical analyses

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

statistical analysis comparisons

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

homa

-0.42

uç

-0.41

araoh

-0.37

 geweest

-0.35

httphttps

-0.35

 polished

-0.35

neck

-0.34

 neck

-0.34

mitives

-0.33

Notae

-0.33

POSITIVE LOGITS

oa̍t

0.63

ScopeManager

0.57

 Kombin

0.56

 IFTT

0.53

MeasureSpec

0.50

 CreateTagHelper

0.48

يكب

0.48

 autorytatywna

0.47

YourGuide

0.47

 Kombination

0.47

Activations Density 0.318%

scientific terms and statistical analyses

statistical analysis comparisons

No Comments

No Known Activations