INDEX

Explanations

numerical data or statistics

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

symbols and dashes

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

 AssemblyCulture

-0.75

 invokingState

-0.60

thâu

-0.49

stylers

-0.48

 endblock

-0.48

+#+#

-0.47

 utafitiHapana

-0.44

 snippetHide

-0.44

WriteTagHelper

-0.44

 ویکی‌آمباردا

-0.41

POSITIVE LOGITS

GenerationType

0.45

賀状

0.43

"]]

0.42

verifyException

0.42

 Lark

0.40

 Crouch

0.38

tonode

0.38

resizingMask

0.38

disp

0.37

interactive

0.37

Activations Density 0.075%

numerical data or statistics

symbols and dashes

No Comments

No Known Activations