INDEX

Explanations

terms related to bleeding and blood clotting.

oai_token-act-pair · gemini-1.5-flash Triggered by @johnny

terms and phrases related to medical conditions and treatments.

oai_token-act-pair · deepseek-r1-dist-llama-70b Triggered by @johnny

medical terms related to bleeding and coagulation

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

bleed

np_max-act-logits · gpt-4.1-nano Triggered by @johnny

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 externi

-0.64

 estekak

-0.64

Filmographie

-0.61

 समीक्षाओं

-0.61

 compri

-0.60

 initComponents

-0.59

 Administrativna

-0.58

شهاد

-0.57

 Wicidata

-0.57

httphttps

-0.56

POSITIVE LOGITS

 bleed

0.71

dinga

0.64

 Aboriginal

0.62

 Indigenous

0.58

 Philippine

0.58

ymce

0.57

bleed

0.57

]-->

0.57

niger

0.57

 bleeds

0.56

Activations Density 2.780%

terms related to bleeding and blood clotting.

terms and phrases related to medical conditions and treatments.

medical terms related to bleeding and coagulation

bleed

No Comments

No Known Activations