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

0:0.09

1:0.11

2:0.08

3:0.07

4:0.10

5:0.35

6:0.08

7:0.09

Negative Logits

 AssemblyTitle

-0.49

írus

-0.40

harusnya

-0.40

GEBURTS

-0.35

minecraft

-0.35

 Koko

-0.35

SOF

-0.35

CMC

-0.35

Koko

-0.34

 становника

-0.34

POSITIVE LOGITS

 unknownFields

0.43

ThroughAttribute

0.41

rungsseite

0.38

مقاله

0.33

ｙ

0.32

matchCondition

0.32

 Hens

0.32

 HasFactory

0.31

LookAnd

0.31

gameserver

0.31

Activations Density 0.000%

No Known Activations

This feature has no known activations.