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

0:0.15

1:0.19

2:0.10

3:0.09

4:0.10

5:0.06

6:0.10

7:0.16

Negative Logits

NameInMap

-0.57

 المعيارى

-0.56

ABASES

-0.56

RegistryLite

-0.54

:✨

-0.54

addPreferredGap

-0.54

 незавершена

-0.54

DATABASES

-0.51

 snippetHide

-0.51

')),

-0.51

POSITIVE LOGITS

padek

0.46

 خارجية

0.44

Искәрмәләр

0.43

is

0.41

Rujukan

0.41

is

0.41

kab

0.40

 Дом

0.40

king

0.39

“”

0.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.