INDEX

Explanations

mathematical equations and notations

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

Equations in brackets

np_acts-logits-general · gemini-2.0-flash

expressions (\[eq:indg\]) and (\[eq:statstat\]))

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

 surla

-0.50

complexContent

-0.49

ကိုးကား

-0.43

 culturelles

-0.43

 initComponents

-0.43

Utf

-0.40

قایناق‌لار

-0.39

ScopeManager

-0.38

chtete

-0.37

 florales

-0.37

POSITIVE LOGITS

VersionUID

0.66

 StatefulWidget

0.60

TagMode

0.60

 AssemblyTitle

0.59

SuppressLint

0.56

 SYLLABLE

0.54

最快更新

0.52

 BoxFit

0.50

imageshack

0.49

subpackage

0.49

Activations Density 1.071%

mathematical equations and notations

Equations in brackets

expressions (\[eq:indg\]) and (\[eq:statstat\]))

No Comments

No Known Activations