INDEX

Explanations

elements and attributes related to structured data representation

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

code and scientific citations

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

 propOrder

-0.72

MessageOf

-0.60

fjspx

-0.58

⤹

-0.54

 Biôgrafia

-0.50

ScopeManager

-0.47

CppMethod

-0.46

addGap

-0.45

uxxxx

-0.44

POSITIVE LOGITS

truded

0.39

caten

0.39

 onCreateView

0.38

Iro

0.36

ledem

0.35

ntlet

0.35

cred

0.34

 crédit

0.34

 crédito

0.34

bli

0.33

Activations Density 0.004%

elements and attributes related to structured data representation

code and scientific citations

No Comments

No Known Activations