INDEX

Explanations

terms related to health conditions and their treatments

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

found in scientific or technical contexts

np_acts-logits-general · gemini-2.0-flash

medical terms and specific entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

elemField

-0.62

tonode

-0.55

 jsPsych

-0.52

 ExecuteAsync

-0.49

 Wikimedijinoj

-0.49

 ligiloj

-0.46

addPreferredGap

-0.46

المكان

-0.46

RTDA

-0.46

CheckBreak

-0.45

POSITIVE LOGITS

BufferException

0.46

Ӕ

0.42

 GenerationType

0.41

TProtocol

0.41

➟

0.41

 novel

0.39

RectangleBorder

0.39

 Novel

0.35

 *)__

0.35

″]

0.35

Activations Density 1.059%

terms related to health conditions and their treatments

found in scientific or technical contexts

medical terms and specific entities

No Comments

No Known Activations