INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 tartalomajánló

-0.61

 énergétique

-0.60

ust

-0.60

 Wikimedijinoj

-0.55

 Framing

-0.53

:✨

-0.53

 kasarigan

-0.52

ímp

-0.52

__["

-0.52

richTextPanel

-0.51

POSITIVE LOGITS

TextAppearance

2.16

 TextAppearance

2.06

Efq

0.72

UnusedPrivate

0.68

 بيها

0.67

neſs

0.67

Personendaten

0.66

новништво

0.65

 houſe

0.65

 Chriftian

0.64

Activations Density 0.001%

No Comments

No Known Activations