INDEX

Explanations

references to programming objects or elements related to development frameworks

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

user input in code/technical contexts

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

Deque

-0.54

InputBorder

-0.53

 autorytatywna

-0.46

KommentareTeilen

-0.45

Batis

-0.44

الإنجليزية

-0.44

inSlope

-0.43

 assemb

-0.43

addPreferredGap

-0.42

ьажоргаш

-0.42

POSITIVE LOGITS

Открыть

0.64

CppMethod

0.44

 vidare

0.43

FXML

0.42

Kariera

0.40

 getItemCount

0.40

 utafitiHapana

0.40

 AssemblyVersion

0.40

primaryStage

0.39

rspec

0.39

Activations Density 0.000%

references to programming objects or elements related to development frameworks

user input in code/technical contexts

No Comments

No Known Activations