INDEX

Explanations

references to programming projects and tools

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

to use or handle

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 chronic

-0.35

 Quer

-0.30

Utf

-0.29

est

-0.29

 REST

-0.28

 quer

-0.27

 curb

-0.27

ệt

-0.26

Хро

-0.26

しくない

-0.26

POSITIVE LOGITS

WithIOException

0.86

adaptiveStyles

0.73

tinyos

0.71

 للمعارف

0.69

<unused14>

0.58

<unused42>

0.58

<unused43>

0.58

<unused41>

0.58

<pad>

0.58

<unused23>

0.58

Activations Density 0.026%

references to programming projects and tools

to use or handle

No Comments

No Known Activations