INDEX

Explanations

numerical values and relevant terms related to measurements or quantities in scientific contexts

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

Occurrences after numbers or symbols

np_acts-logits-general · gemini-2.0-flash

middle and manual action

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 extreme

-0.65

extreme

-0.62

Extreme

-0.54

 Extreme

-0.52

 extrême

-0.51

issime

-0.49

究極

-0.48

 تانيه

-0.48

Tiny

-0.46

 legendary

-0.46

POSITIVE LOGITS

 moderate

0.78

mid

0.73

 lenker

0.72

 intermediate

0.71

 middle

0.70

 medium

0.70

Moderate

0.70

 moderately

0.70

 intermédiaire

0.69

 Moderate

0.66

Activations Density 0.426%

numerical values and relevant terms related to measurements or quantities in scientific contexts

Occurrences after numbers or symbols

middle and manual action

No Comments

No Known Activations