INDEX

Explanations

mentions of specific geographical locations or landmarks

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

"Ba" followed by various characters

np_acts-logits-general · gemini-2.0-flash

Ba prefix in various contexts

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

ollectionView

-0.55

뀜

-0.53

ListItemIcon

-0.53

Presentation

-0.51

 Presentations

-0.51

 IActionResult

-0.49

 Presentation

-0.49

jeni

-0.47

ogaster

-0.45

 Displays

-0.45

POSITIVE LOGITS

Ba

0.77

 disambiguazione

0.73

]^{-

0.71

hadur

0.70

 Baek

0.69

pyrene

0.69

baf

0.69

BAH

0.68

Ba

0.66

Baf

0.66

Activations Density 0.089%

mentions of specific geographical locations or landmarks

"Ba" followed by various characters

Ba prefix in various contexts

No Comments

No Known Activations