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

-0.41

-0.40

mo

-0.39

-0.38

-0.37

-0.35

 inwoners

-0.35

↵

-0.35

POSITIVE LOGITS

PerformLayout

1.21

sizeCache

1.09

TagMode

1.09

SharedDtor

1.08

TypedDataSet

1.06

RTLR

1.05

 дописавши

1.05

Efq

1.05

writeFieldEnd

1.04

ThroughAttribute

1.03

Activations Density 0.000%

No Known Activations

This feature has no known activations.