INDEX

Explanations

acronyms and technical terms related to scientific research and organizations

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

Acronyms and abbreviations

np_acts-logits-general · gemini-2.0-flash

abbreviations followed by numbers or symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

TargetException

-0.52

onaceous

-0.47

 anything

-0.46

 تانيه

-0.45

reich

-0.43

限り

-0.42

 nothing

-0.42

 zvuky

-0.41

HKEY

-0.41

letzt

-0.40

POSITIVE LOGITS

DockStyle

0.97

paravant

0.72

 abbre

0.69

 typelib

0.68

 zelve

0.67

 Combien

0.66

 dezelve

0.66

备案

0.64

rsiniz

0.63

 meriva

0.62

Activations Density 1.224%

acronyms and technical terms related to scientific research and organizations

Acronyms and abbreviations

abbreviations followed by numbers or symbols

No Comments

No Known Activations