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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.29

戸

-0.29

 lawns

-0.28

$(

-0.28

}}^{

-0.28

bpy

-0.28

enumerate

-0.27

$\

-0.27

 lawn

-0.26

POSITIVE LOGITS

ArgsConstructor

4.50

rungsseite

0.99

 initComponents

0.97

 AssemblyCompany

0.87

StoryboardSegue

0.85

dataclass

0.85

AndroidJUnit

0.82

Autowired

0.82

Parcelize

0.82

setVerticalGroup

0.81

Activations Density 0.000%

No Known Activations

This feature has no known activations.