INDEX

Explanations

indicators of milestones or significant updates in a structured format

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

Code or special characters

np_acts-logits-general · gemini-2.0-flash

quotations and code

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 }^{[

-0.64

 neceſſ

-0.58

 pleaf

-0.55

 ſen

-0.54

 ſtand

-0.54

Guia

-0.54

 theſe

-0.52

 poffible

-0.52

emann

-0.51

 anſ

-0.51

POSITIVE LOGITS

tagHelperRunner

0.77

#+#

0.72

 الحره

0.68

 JpaRepository

0.62

awaiter

0.62

 متعلقه

0.61

ymce

0.60

 חיצוניים

0.57

 typelib

0.56

PMailer

0.55

Activations Density 0.083%

indicators of milestones or significant updates in a structured format

Code or special characters

quotations and code

No Comments

No Known Activations