The counting and (upper) mass dimensions are notions of dimension for subsets of $mathbb{Z}^d$. We develop their basic properties and give a characterization of the counting dimension via coverings. In addition, we prove Marstrand-type results for both dimensions. For example, if $A subseteq mathbb{R}^d$ has counting dimension $D(A)$, then for almost every orthogonal projection with range of dimension $k$, the counting dimension of the image of $A$ is at least $min big(k,D(A)big)$. As an application, for subsets $A_1, ldots, A_d$ of $mathbb{R}$, we are able to give bounds on the counting and mass dimensions of the sumset $c_1 A_1 + cdots + c_d A_d$ for Lebesgue-almost every $c in mathbb{R}^d$. This work extends recent work of Y. Lima and C. G. Moreira.