INDEX

Explanations

statements or quotes attributed to speakers

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

reporting statements

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

windowFixed

-0.66

migrationBuilder

-0.64

msgTypes

-0.63

ViewImports

-0.63

niſſe

-0.63

 defaultstate

-0.61

TagMode

-0.61

ſſung

-0.60

 незавершена

-0.60

rungsseite

-0.60

POSITIVE LOGITS

 spot

0.30

 rapport

0.26

centerY

0.26

 Gegensatz

0.25

 umge

0.25

 dikel

0.25

postsleuth

0.25

 uzman

0.24

 prospect

0.24

eql

0.24

Activations Density 0.008%

statements or quotes attributed to speakers

reporting statements

No Comments

No Known Activations