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

0:0.12

1:0.14

2:0.11

3:0.10

4:0.13

5:0.10

6:0.12

7:0.14

Negative Logits

 douceur

-0.28

 vícti

-0.27

 scomp

-0.26

 vertes

-0.24

 restant

-0.24

 geblieben

-0.23

 touché

-0.23

 veter

-0.23

 touche

-0.23

 sauvages

-0.23

POSITIVE LOGITS

AnimationsModule

0.42

 виправивши

0.40

awtextra

0.36

GraphicsUnit

0.36

новниш

0.35

 gynhyrchwyd

0.35

SequentialGroup

0.35

crollView

0.35

CloseOperation

0.35

minecraftforge

0.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.