INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itſelf

-1.33

 myſelf

-1.24

 raiſ

-1.16



-1.15

 Phry

-1.15

 Mahomet

-1.13

 pleaſure

-1.12

 Houſe

-1.12

 doubtnut

-1.11

 Shakspeare

-1.09

POSITIVE LOGITS

the

2.01

The

1.45

The

1.30

THE

1.28

 same

1.14

the

1.05

1.01

ethe

0.98

new

0.97

enthe

0.96

Activations Density 0.000%

No Known Activations

This feature has no known activations.