In GrowthBook, the concept of "namespaces" is used to isolate experiments and avoid users being exposed to multiple experiments that may conflict with each other. A namespace is a way to make conflicting experiments mutually exclusive. Users are randomly assigned a value from 0 to 1 for each namespace. Each experiment in a namespace has a range of values that it includes. Users are only part of an experiment if their value falls within the experiment's range. As long as two experiment ranges do not overlap, users will only ever be in at most one of them [[source](https://docs.growthbook.io/feature-flag-experiments#namespaces)]. The term "group" is not explicitly defined in the provided sources in the context of GrowthBook. However, in general experimentation terminology, a "group" often refers to a set of users who are exposed to a particular variant in an experiment. This is different from a namespace, which is a mechanism to ensure that users are only exposed to one experiment within a set of potentially conflicting experiments. It's important to note that namespaces need to be configured under SDK Configuration → Namespaces in the GrowthBook UI's left navigation bar before they can be used [[source](https://docs.growthbook.io/features/rules#namespaces)]. In a forum conversation, it was also mentioned that you can intentionally overlap a namespace if you want to, for example, to keep a group of users unexposed to any experiments [[source](https://linen.growthbook.io/t/10133376/is-there-a-way-to-randomly-but-consistently-divide-users-int)]. Please refer to the official GrowthBook documentation or forum for more specific details or updates.