INDEX

Explanations

names and technical terms related to biology and medicine

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

abbreviations and initialisms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 informée

-0.55

 ProtoMessage

-0.52

Eksteraj

-0.51

enumii

-0.51

حياتها

-0.50

Rhestr

-0.50

Ārējās

-0.49

-------

-0.49

 autorytatywna

-0.49

__*/

-0.49

POSITIVE LOGITS

 held

0.36

isContained

0.36

TestingModule

0.35

 wyda

0.35

oredCriteria

0.34

 Brea

0.31

hid

0.31

 buck

0.30

cha

0.30

 accused

0.30

Activations Density 0.117%

names and technical terms related to biology and medicine

abbreviations and initialisms

No Comments

No Known Activations