In the present study, we examined whether an ongoing primary task is inhibited when switching to an interruption task. To this end, we implemented the n-2 backward inhibition paradigm (Mayr & Keele, 2001) into a task-interruption situation. Subjects performed two primary tasks comprising a pre-defined sequence of three subtasks (e.g., ABC). There were non-interrupted and interrupted primary tasks. In interrupted primary tasks, an interruption task occurred before the last subtask of a primary task, resulting in a n-2 repetition or a n-2 switch demand in the first post-interruption subtask. We found that switching back from the interruption task to the primary task resulted in n-2 switch costs in the first subtask after the interruption. This finding indicates that the last subtask performed before the interruption remains activated rather than being inhibited when switching to the interruption task.