INDEX

Explanations

database-related terms and query identifiers

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

joint table names like form, r, INV, OINV

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

SourceChecksum

-0.93

AndEndTag

-0.91

(!__

-0.79

AutoScaleMode

-0.73

CppMethod

-0.71

]");

-0.70

thâu

-0.68

DebuggerStep

-0.66

*/;

-0.66

 ویکی‌پدی

-0.66

POSITIVE LOGITS

 المعيارى

0.59

ußer

0.56

 knex

0.54

AddHtmlAttribute

0.52

WriteAttribute

0.51

vrouw

0.51

 Adolfo

0.48

 mitral

0.47

migrationBuilder

0.47

 beech

0.47

Activations Density 0.029%

database-related terms and query identifiers

joint table names like form, r, INV, OINV

No Comments

No Known Activations