INDEX

Explanations

programming or coding-related terms and functions

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

invalidate or revalidate

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

Ikus

-0.55

ագրություններ

-0.54

AndroidJUnit

-0.54

 CanadaChoose

-0.53

 disambiguazione

-0.51

AutoScaleMode

-0.50

queles

-0.49

nloa

-0.49

ckså

-0.49

 autorytatywna

-0.49

POSITIVE LOGITS

invalidate

2.39

 invalidate

1.63

Invalidate

1.58

repaint

0.88

revalidate

0.61

 INVALID

0.57

 totalSupply

0.56

INVALID

0.54

%");

0.48

$")

0.48

Activations Density 0.002%

programming or coding-related terms and functions

invalidate or revalidate

No Comments

No Known Activations