Cluster analysis plays a foremost role in identifying groups of genes that show similar behavior under a set of experimental conditions. Several clustering algorithms have been proposed for identifying gene behaviors and to understand their significance. The principal aim of this work is to develop an intelligent rough clustering technique, which will efficiently remove the irrelevant dimensions in a high-dimensional space and obtain appropriate meaningful clusters. This paper proposes a novel biclustering technique that is based on rough set theory. The proposed algorithm uses correlation coefficient as a similarity measure to simultaneously cluster both the rows and columns of a gene expression data matrix and mean squared residue to generate the initial biclusters. Furthermore, the biclusters are refined to form the lower and upper boundaries by determining the membership of the genes in the clusters using mean squared residue. The algorithm is illustrated with yeast gene expression data and the experiment proves the effectiveness of the method. The main advantage is that it overcomes the problem of selection of initial clusters and also the restriction of one object belonging to only one cluster by allowing overlapping of biclusters.