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

AddHtmlAttribute

-0.41

richTextPanel

-0.38

httphttps

-0.35

InputTagHelper

-0.35

ConstraintMaker

-0.34

outState

-0.32

💼

-0.32

InSection

-0.31

 robust

-0.31

(":");

-0.31

POSITIVE LOGITS

 Baillargeon

0.58

bleven

0.53

 الرياضيه

0.52

 Numerade

0.51

 contentType

0.48

ſelves

0.47

vangen

0.46

iſen

0.44

 fubject

0.44

GraphicsUnit

0.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.