INDEX

Explanations

numerical values and identifiers related to medical or health metrics

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

hexadecimal numbers and code structures

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UrlResolution

-0.69

-0.61

errHandler

-0.57

RenderAtEndOf

-0.57

principalColumn

-0.53

angliski

-0.52

XmlAccessType

-0.51

 مشين

-0.51

migrationBuilder

-0.50

 nahilalakip

-0.49

POSITIVE LOGITS

 GenerationType

0.55

 sencillo

0.38

sidemargin

0.36

 sencillos

0.34

 bornes

0.32

VersionUID

0.32

Dro

0.30

uğ

0.29

Nel

0.29

addContainerGap

0.29

Activations Density 0.215%

numerical values and identifiers related to medical or health metrics

hexadecimal numbers and code structures

No Comments

No Known Activations