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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.15

1:0.14

2:0.11

3:0.08

4:0.08

5:0.05

6:0.12

7:0.22

Negative Logits

 />";

-0.27

DEAR

-0.25

fli

-0.25

Hoh

-0.24

 Responsibility

-0.24

UW

-0.24

ритори

-0.24

 Combien

-0.24

ColumnHeaders

-0.24

POSITIVE LOGITS

 دیکھیے

0.33

 HasFactory

0.31

 VIAF

0.29

DeleteBehavior

0.28

putchar

0.27

 sanitaria

0.27

<bos>

0.27

resave

0.27

steamcommunity

0.26

ESOME

0.26

Activations Density 0.000%

No Known Activations

This feature has no known activations.