INDEX

Explanations

references to specific programming or coding elements

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

leptonic, Peru, technical terms

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

verwijspagina

-0.53

FormTagHelper

-0.53

ɵɵelementStart

-0.47

ParallelGroup

-0.47

ipelago

-0.46

̈́

-0.45

 AttributeSet

-0.45

 CreateTagHelper

-0.45

TagMode

-0.44

 يتيمه

-0.43

POSITIVE LOGITS

abestanden

0.55

mtrl

0.49

TypeDef

0.47

XtraGrid

0.44

dafx

0.41

XtraReports

0.41

 FishBase

0.40

 peruan

0.39

Peru

0.39

Cele

0.39

Activations Density 0.002%

references to specific programming or coding elements

leptonic, Peru, technical terms

No Comments

No Known Activations