INDEX

Explanations

terms related to scientific processes and classifications

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

scientific research and measurement

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

principalColumn

-0.86

LookAnd

-0.75

ChildScrollView

-0.74

IntoConstraints

-0.73

 resourceCulture

-0.72

uxxxx

-0.70

 وتسجيلات

-0.70

__':

-0.68

 للاسماء

-0.68

تقاوى

-0.68

POSITIVE LOGITS

it

0.37

 gard

0.37

Auto

0.36

ELS

0.35

 GARD

0.35

rat

0.34

Al

0.33

Â

0.33

fusc

0.33

put

0.33

Activations Density 0.384%

terms related to scientific processes and classifications

scientific research and measurement

No Comments

No Known Activations