INDEX

Explanations

references to various entities or topics related to the term "Za."

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

Tokens starting with "Za"

np_acts-logits-general · gemini-2.0-flash

ZA or Za variations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Vidite

-0.59

 betweenstory

-0.56

 سكانية

-0.54

roek

-0.54

uxxxx

-0.53

Demografia

-0.53

 Wrench

-0.53

 Meksiku

-0.52

ITHUB

-0.52

 pulumi

-0.52

POSITIVE LOGITS

 BoxDecoration

0.56

tableFuture

0.54

ionados

0.53

mentioned

0.50

 समीक्षाएं

0.47

anger

0.47

IsContent

0.46

inger

0.46

wound

0.45

 anecd

0.45

Activations Density 0.021%

references to various entities or topics related to the term "Za."

Tokens starting with "Za"

ZA or Za variations

No Comments

No Known Activations