INDEX

Explanations

terms related to image matching and feature detection methods

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

Structure-from-Motion

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

audio

-0.38

 audio

-0.35

 lembar

-0.33

Issue

-0.32

 issue

-0.32

issue

-0.32

 gewöhnlich

-0.31

programa

-0.31

Ann

-0.31

 aussch

-0.31

POSITIVE LOGITS

AddTagHelper

0.68

bootstrapcdn

0.67

 ModelExpression

0.67

 незавершена

0.66

LookAnd

0.63

RenderAtEndOf

0.61

 BoxFit

0.61

EndContext

0.61

StoryboardSegue

0.61

IsMutable

0.60

Activations Density 0.189%

terms related to image matching and feature detection methods

Structure-from-Motion

No Comments

No Known Activations