INDEX

Explanations

terms related to diagnostic and detection processes in medical contexts

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

Detecting or predicting something

np_acts-logits-general · gemini-2.0-flash

detecting and counting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 вікі

-0.53

moveToFirst

-0.50

 accuracy

-0.46

httphttps

-0.45

ikistan

-0.45

 eletr

-0.45

hpur

-0.43

insp

-0.43

CreateMap

-0.42

 analyte

-0.41

POSITIVE LOGITS

AndEndTag

0.51

BufferException

0.50

⎨

0.44

__":

0.43

Nationalité

0.40

 pungkas

0.38

Produzione

0.37

 semula

0.37

twimg

0.36

 pungkasnya

0.36

Activations Density 2.094%

terms related to diagnostic and detection processes in medical contexts

Detecting or predicting something

detecting and counting

No Comments

No Known Activations