INDEX

Explanations

No Explanations Found

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

AddTagHelper

-0.66

tanleria

-0.54

Clik

-0.51

 الحره

-0.50

 كومونز

-0.48

WaitGroup

-0.47

Transkript

-0.47

 Reform

-0.44

OGND

-0.44

verwijspagina

-0.43

POSITIVE LOGITS

0.62

 šal

0.50

 Keuangan

0.46

 campur

0.45

 temporadas

0.45

 psicológica

0.44

 ferons

0.43

 jaringan

0.43

 plantillas

0.43

 económicas

0.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.