INDEX

Explanations

game mechanics related to character progression and resource management

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

various languages and types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 betweenstory

-0.75

ंदीखरीदारी

-0.68

SourceChecksum

-0.68

webElementXpaths

-0.63

RegressionTest

-0.62

 Biôgrafia

-0.61

 createSlice

-0.57

AccessorTable

-0.56

modb

-0.56

Hentet

-0.55

POSITIVE LOGITS

 various

0.43

 berbagai

0.40

 çeşitli

0.38

 verschiedene

0.37

Various

0.36

various

0.34

 VARIOUS

0.34

 Various

0.33

 verschiedenen

0.33

 Fähig

0.33

Activations Density 0.015%

game mechanics related to character progression and resource management

various languages and types

No Comments

No Known Activations