INDEX

Explanations

words and phrases related to significant events or actions

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

an old-fashioned skill

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

 indisponible

-0.53

XmlAttribute

-0.53

出版年

-0.51

sprzedam

-0.50

PerformLayout

-0.48

SaveChangesAsync

-0.48

institute

-0.46

publ

-0.46

 '\\;'

-0.45

فایل‌لار

-0.45

POSITIVE LOGITS

TypedDataSet

0.40

tagHelperRunner

0.39

0.38

mergeFrom

0.36

 kohdetta

0.35

<h1>

0.35

httphttps

0.35

JspWriter

0.34

 mußten

0.33

setContentView

0.31

Activations Density 0.008%

words and phrases related to significant events or actions

an old-fashioned skill

No Comments

No Known Activations