INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

httphttps

-0.72

PerformLayout

-0.66

 totalCount

-0.66

GraphicsUnit

-0.65

MLLoader

-0.65

 AssemblyCompany

-0.65

 faſt

-0.62

 BoxDecoration

-0.61

fjspx

-0.61

 maxHeight

-0.60

POSITIVE LOGITS

1.27

\_

0.90

0.77

‐

0.75

0.72

_{

0.67

‑

0.66

}_

0.65

・

0.62

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.