INDEX

Explanations

mathematical symbols and notations

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

equations, mathematical expressions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bufio

-0.66

ViewInit

-0.63

tagHelperRunner

-0.63

RTEE

-0.61

 endwhile

-0.60

ChildScrollView

-0.60

 fusca

-0.59

AnimationsModule

-0.58

IntoConstraints

-0.58

styleUrls

-0.57

POSITIVE LOGITS

 Lingkungan

0.42

<tr>

0.40

 Púb

0.40

 Público

0.40

 Veuillez

0.38

 møte

0.37

 bâtiments

0.36

First

0.36

 Reykjav

0.35

 Catedral

0.35

Activations Density 0.014%

mathematical symbols and notations

equations, mathematical expressions

No Comments

No Known Activations