INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

المكان

-0.41

 Aman

-0.40

Ass

-0.38

 Charger

-0.38

 Bang

-0.37

 Roman

-0.37

 Raman

-0.37

 Respond

-0.37

 nest

-0.36

 theater

-0.36

POSITIVE LOGITS

 Grecs

0.44

 dieux

0.42

 fumée

0.42

 réfugiés

0.41

 démocr

0.41

__);

0.41

 chrétiens

0.40

 fidèles

0.38

protoimpl

0.38

 dirigeants

0.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.