INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_18/width_65k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.18.hook_mlp_out

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

 >=",

-0.59

 المعيارى

-0.48

LEncoder

-0.47

 Brice

-0.47

arias

-0.47

Hardcover

-0.45

istert

-0.44

kannya

-0.44

MLLoader

-0.44

seamnă

-0.43

POSITIVE LOGITS

 Roskov

0.62

MergeFrom

0.54

ttino

0.53

 initComponents

0.52

DBNull

0.52

addPreferredGap

0.52

ajemy

0.51

مقاله

0.51

+#+#

0.51

mapStateToProps

0.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.