INDEX

Explanations

numerical data related to articles or web content

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Fractions or ratios

np_acts-logits-general · gemini-2.0-flash

numbers followed by slash

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

-0.75

-0.71

-0.69

-0.68

-0.65

↵↵

-0.64

-0.63

-0.62

-0.61

POSITIVE LOGITS

ValueStyle

1.37

 nahilalakip

1.22

GEBURTSDATUM

1.22

 الرياضيه

1.21

ſelves

1.20

 myſelf

1.20

+#+#

1.19

Personensuche

1.17

Efq

1.15

 pleaſure

1.15

Activations Density 0.470%

numerical data related to articles or web content

Fractions or ratios

numbers followed by slash

No Comments

No Known Activations