INDEX

Explanations

references to health-related issues or symptoms

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

Unexplained medical symptoms or emergencies

np_acts-logits-general · gemini-2.0-flash

unusual or unexplained conditions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

setVerticalGroup

-0.62

ISupport

-0.53

godic

-0.50

Res

-0.47

 zalo

-0.46

 تضيفلها

-0.46

ulti

-0.45

فر

-0.45

</thead>

-0.45

 krav

-0.45

POSITIVE LOGITS

 suspiciously

0.99

 unexplained

0.97

 suddenly

0.90

 unusually

0.89

 unusual

0.89

Unusual

0.87

 suspicious

0.87

 plötzlich

0.85

unusual

0.85

 merkwür

0.84

Activations Density 0.361%

references to health-related issues or symptoms

Unexplained medical symptoms or emergencies

unusual or unexplained conditions

No Comments

No Known Activations