INDEX

Explanations

programming-related terms and code structure elements

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

C++ code components

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

 kasarigan

-0.73

 pinulongan

-0.65

GraphicsUnit

-0.65

 BoxDecoration

-0.61

CodeAttribute

-0.58

 оригіналу

-0.57

AndEndTag

-0.57

帖最后由

-0.56

enumii

-0.55

styleType

-0.55

POSITIVE LOGITS

NameInMap

0.80

 createSlice

0.62

exitRule

0.61

 ProtoMessage

0.60

SourceChecksum

0.57

 TestBed

0.56

 censiti

0.56

 XCTest

0.50

hObject

0.49

 MediatR

0.49

Activations Density 0.072%

programming-related terms and code structure elements

C++ code components

No Comments

No Known Activations