INDEX

Explanations

specific numerical and mathematical representations or indicators

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

numbers and units

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

دانشنامهٔ

-0.46

bitos

-0.40

zzazione

-0.39

alnız

-0.39

 Strong

-0.39

 XCTest

-0.38

trong

-0.36

VIAF

-0.36

 reversed

-0.35

Sap

-0.35

POSITIVE LOGITS

Personensuche

0.54

parsedMessage

0.52

contentLoaded

0.51

')")

0.50

stateMutability

0.50

 resourceCulture

0.48

ագրություններ

0.46

DoubleQuotes

0.46

 typelib

0.46

 muualla

0.45

Activations Density 0.098%

specific numerical and mathematical representations or indicators

numbers and units

No Comments

No Known Activations