Machine learning has become a popular instrument for the identification of dark matter candidates at particle collider experiments. They enable the processing of large datasets and are therefore suitable to operate directly on raw data coming from the detector, instead of reconstructed objects. Here, we investigate patterns of raw pixel hits recorded by the Belle II pixel detector, that is operational since 2019 and presently features 4 M pixels and trigger rates up to 5 kHz. In particular, we focus on unsupervised techniques that operate without the need for a theoretical model. These model-agnostic approaches allow for an unbiased exploration of data, while filtering out anomalous detector signatures that could hint at new physics scenarios. We present the identification of hypothetical magnetic monopoles against Belle II beam background using Self-Organizing Kohonen Maps and Autoencoders. The two unsupervised algorithms are compared to a convolutional Multilayer Perceptron and a superior signal efficiency is found at high background rejection levels. Our results strengthen the case for using unsupervised machine learning techniques to complement traditional search strategies at particle colliders and pave the way to potential online applications of the algorithms in the near future.