INDEX

Explanations

numerical data, particularly related to measurements or statistical values

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

Values with plus-minus signs

np_acts-logits-general · gemini-2.0-flash

medical data measurements

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

thenReturn

-0.68

 resourceCulture

-0.63

RunWith

-0.60

RegressionTest

-0.60

Zusammenfassung

-0.59

adaptiveStyles

-0.58

 MotionEvent

-0.57

IsPostBack

-0.56

convertView

-0.55

antMatchers

-0.54

POSITIVE LOGITS

vician

0.65

存于互联网档案馆

0.59

 Normdatei

0.56

 يتيمه

0.55

 Dign

0.54

 Himo

0.53

ouches

0.51

Mó

0.51

 Enix

0.50

 مواليد

0.49

Activations Density 0.535%

numerical data, particularly related to measurements or statistical values

Values with plus-minus signs

medical data measurements

No Comments

No Known Activations