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

0:0.16

1:0.14

2:0.11

3:0.10

4:0.10

5:0.08

6:0.11

7:0.16

Negative Logits

oa̍t

-0.52

 ProtoMessage

-0.50

 kaarangay

-0.48

richTextPanel

-0.46

 Roskov

-0.46

SharedDtor

-0.45

ThroughAttribute

-0.44

matchCondition

-0.44

 betweenstory

-0.44



-0.43

POSITIVE LOGITS

 heet

0.29

bara

0.27

omena

0.26

://"

0.25

ξα

0.25

 пропа

0.25

 plano

0.25

XI

0.24

 plan

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.