INDEX

Explanations

keywords related to programming and technical concepts

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

programming and science terms

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

httphttps

-0.89

 للاسماء

-0.88

rungsseite

-0.86

RegistryLite

-0.85

styleType

-0.81

<unused28>

-0.79

<unused41>

-0.78

<unused74>

-0.78

<unused17>

-0.78

<unused14>

-0.78

POSITIVE LOGITS

<eos>

0.28

maks

0.28

ACGIH

0.25

Trung

0.23

Thời

0.23

koe

0.22

icidio

0.22

STOT

0.22

 decis

0.22

qPCR

0.22

Activations Density 0.099%

keywords related to programming and technical concepts

programming and science terms

No Comments

No Known Activations