INDEX

Explanations

the beginning of new sections or changes in content format within the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Numbers, especially with math symbols

np_acts-logits-general · gemini-2.0-flash

code/programming snippets

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 also

-0.45

jakarta

-0.42

 animés

-0.41

 sanitaires

-0.40

đa

-0.40

ningens

-0.40

IBAction

-0.40

cier

-0.39

elar

-0.39

 Ausgang

-0.39

POSITIVE LOGITS

StoryboardSegue

1.00

 MenuView

0.94

AddTagHelper

0.84

 OFDb

0.82

__':

0.81

 resourceCulture

0.81

 beginnetje

0.80

__":

0.76

MessageTagHelper

0.73

 ddelweddau

0.72

Activations Density 0.415%

the beginning of new sections or changes in content format within the text

Numbers, especially with math symbols

code/programming snippets

No Comments

No Known Activations