INDEX

Explanations

No Explanations Found

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

vů

-0.42

 extranjera

-0.39

ACHUSETTS

-0.38

 Boden

-0.37

 küche

-0.37

 competition

-0.37

setLeft

-0.36

 Reſ

-0.36

 Cold

-0.36

 Inſ

-0.35

POSITIVE LOGITS

TabIndex

5.66

UseVisualStyle

1.06

 resourceCulture

1.03

 nahilalakip

0.92

 AssemblyTitle

0.91

adaptiveStyles

0.90

 CreateTagHelper

0.89

parsedMessage

0.87

ValueStyle

0.87

 kasarigan

0.87

Activations Density 0.000%

No Known Activations

This feature has no known activations.