INDEX

Explanations

terms related to scientific concepts and medical research

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

preceding specific nouns

np_acts-logits-general · gemini-2.0-flash

concepts and specific terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.59

-0.52

haped

-0.51

-0.50

-0.49

pecific

-0.47

</strong>

-0.47

Le

-0.45

POSITIVE LOGITS

تقاوى

0.91

featureID

0.91

 houſe

0.88

 Jefus

0.86

 myſelf

0.84

 againſt

0.83

 ſche

0.81

 NDEBUG

0.80

 pinulongan

0.79

 Reſ

0.79

Activations Density 1.694%

terms related to scientific concepts and medical research

preceding specific nouns

concepts and specific terms

No Comments

No Known Activations