INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-att-16k

Configuration

google/gemma-scope-2b-pt-att/layer_10/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.attn.hook_z

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

Head Attr Weights

0:0.12

1:0.13

2:0.12

3:0.12

4:0.11

5:0.12

6:0.12

7:0.12

Negative Logits

 AssemblyCulture

-0.45

+#+#

-0.40

RegressionTest

-0.40

 Réponses

-0.39

 CreateTagHelper

-0.38

RectangleBorder

-0.38

vernight

-0.38

getDescriptor

-0.35

addCriterion

-0.35

EndProject

-0.34

POSITIVE LOGITS

RenderAtEndOf

0.30

 Вікі

0.29

 fédé

0.28

లాలు

0.27

 saper

0.27

 however

0.27

]")]

0.27

례

0.26

 scolaires

0.26

 agricoles

0.26

Activations Density 0.000%

No Known Activations

This feature has no known activations.