INDEX

Explanations

data related to statistical analysis or numerical metrics

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

numerical values

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

 surla

-0.89



-0.75

 kasarigan

-0.71

rungsseite

-0.69

+#+#

-0.66

 تضيفلها

-0.65

XmlAccessType

-0.64

 queſta

-0.62

Хьажоргаш

-0.61

 ſind

-0.61

POSITIVE LOGITS

 independientes

0.50

 contribución

0.49

 puntuación

0.48

 independencia

0.47

 démocratique

0.46

 independiente

0.46

 adopción

0.45

 extinción

0.45

 claridad

0.45

 orilla

0.45

Activations Density 0.137%

data related to statistical analysis or numerical metrics

numerical values

No Comments

No Known Activations