INDEX

Explanations

terms related to a specific mathematical or scientific concept

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

centering within documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

InSection

-0.60

 vPvB

-0.56

endpush

-0.49

migrationBuilder

-0.48

XmlType

-0.47

CppCodeGen

-0.45

 MainAxisSize

-0.44



-0.44

JAKARTA

-0.43

waitKey

-0.43

POSITIVE LOGITS

AndEndTag

0.51

 CreateTagHelper

0.43

 novamente

0.42

 للاسماء

0.42

 certificado

0.42

IntoConstraints

0.41

again

0.41

setVerticalGroup

0.41

 Geduld

0.40

 again

0.40

Activations Density 0.000%

terms related to a specific mathematical or scientific concept

centering within documents

No Comments

No Known Activations