INDEX

Explanations

references to programming and software configuration elements

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

Library/package names and related terms

np_acts-logits-general · gemini-2.0-flash

code elements and libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

AppCompat

-0.43

-0.41

-0.37

::

-0.36

-0.35

POSITIVE LOGITS

uxxxx

1.86

parsedMessage

1.38

 виправивши

1.29

 AssemblyCulture

1.29

 Wikimedijinoj

1.23

 للاسماء

1.20

 betweenstory

1.20

WithIOException

1.20

EDEFAULT

1.20

featureID

1.19

Activations Density 1.284%

references to programming and software configuration elements

Library/package names and related terms

code elements and libraries

No Comments

No Known Activations