INDEX

Explanations

metrics and statistical results related to health conditions and medical studies

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

citations and references

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

tagHelperRunner

-0.60

LookAnd

-0.54

 كومونز

-0.49

UnusedPrivate

-0.48

OGND

-0.48

*__

-0.47

GTCX

-0.46

ंदीखरीदारी

-0.44

----</

-0.44

 ویکی‌پدی

-0.43

POSITIVE LOGITS

 Herkunft

0.48

จริงๆ

0.48

ริง

0.48

 alimentaria

0.47

 Larson

0.46

 Weisheit

0.46

 dégâts

0.45

 Innenstadt

0.45

แดง

0.45

 églises

0.45

Activations Density 0.017%

metrics and statistical results related to health conditions and medical studies

citations and references

No Comments

No Known Activations