INDEX

Explanations

numerical values related to software or programming concepts

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

urls and technical identifiers

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

-0.35

 Sélectionnez

-0.28

findpost

-0.28

zeczytaj

-0.24

 Abgerufen

-0.24

on

-0.24

 clínico

-0.24

 literario

-0.24

 hace

-0.23

POSITIVE LOGITS

 CreateTagHelper

0.81

 المعيارى

0.77

 autorytatywna

0.76

 surla

0.73

SharedCtor

0.73

:✨

0.71

NameInMap

0.69

<unused28>

0.69

QMetaType

0.69

<unused3>

0.68

Activations Density 0.006%

numerical values related to software or programming concepts

urls and technical identifiers

No Comments

No Known Activations